Show TOC

 Unified Demand Forecast (UDF) Locate this document in the navigation structure


UDF provides demand modeling and demand forecasting services for SAP Retail applications driven by demand prediction. UDF also provides insights into shopper behavior, enabling retailers to perform predictive analytics on customer demand.

UDF uses near-real-time information about multichannel customer transactions collected in SAP Customer Activity Repository. UDF can use historical demand data from specific time series sources (such as consumption data, point-of-sale data, or sales orders). UDF takes advantage of SAP HANA to provide a unified prediction of future daily demands. For output, UDF generates a demand value plus an accompanying decomposition of demand (such as baseline demand and promotional lifts).

The UDF demand forecasts can serve as the basis for various cross-industry planning use cases.

Implementation Considerations

  • UDF is not specific to any consuming application. Instead, it provides its services through the cross-industry reusable data layer Demand Data Foundation (DDF).

  • Both UDF and DDF are components of SAP Customer Activity Repository.

  • The statistical algorithms of UDF are implemented as an application function library (UDF AFL) that you install and run in the SAP HANA database. The UDF AFL is released independently of the other components, as described in SAP Note 2050229Information published on SAP site.


UDF operates in two main steps:

  1. Demand modeling

    Recommendation Recommendation

    • For input, you should provide 2 years of demand history to ensure the proper interpretation of seasonality, trend, and other yearly demand influencing factors (DIFs).

    • Make sure that your historical data is at daily granularity. Weekly data is currently not supported. For more information, see Customizing (transaction SPRO) under   Cross-Application Components   Demand Data Foundation   Imported Data   Time Series   Define Time Series for Key Figure Configuration  .

    End of the recommendation.

    Taking the historical demand data provided, UDF tries to explain the historical sales and the impact that each DIF had on consumer demand in the past. DIFs can be price changes, promotions, tactics, seasonality, or trend, for example.

    Technically, UDF models demand by estimating the best values for the parameters of its defined statistical model. The parameters typically describe DIF effects. The demand modeling results are written to table /DMF/UMD_PAR.

    Demand modeling is a prerequisite for demand forecasting. Before objects (such as products and locations) can be considered for a forecast, they must first have been modeled.

  2. Demand forecasting

    Using the results from demand modeling and given inputs such as planned promotions and prices, UDF can predict the effects of similar DIF occurrences in the future and derive from those the future demand. UDF can forecast this demand for a specific combination of product / location / sales organization / distribution channel / order channel / day for the time period requested. The impact of each factor that adds up to the total forecast can be detailed out (see Demand Decomposition).

    UDF provides the forecast results to its consuming applications via SAP HANA view Note that you can display and manage SAP HANA views in SAP HANA studio.


Types of Historical Demand Data

UDF supports various time series sources (such as point-of-sale data, consumption data, or sales orders). For more information, see Time Series.

Virtual Data Models (VDMs)

UDF can model and forecast demand using VDM connections to transaction log (TLOG) data in the Multichannel Sales Repository (MCSR) of SAP Customer Activity Repository. The VDMs allow UDF to access historical demand data in that system (such as POS data or sales orders). For more information, see SAP HANA Content for DDF with UDF.


You can run UDF in different modes, depending on your forecast scenario:

  • Production mode: This is the default mode, and you can schedule the forecast run. The forecast results are persisted in the database and can be read directly from SAP HANA views or SAP HANA tables.

  • Diagnostic mode: This mode is for diagnostic evaluations and forecast analyses, such as holdout forecasts. You can schedule the forecast run.

  • What-if forecast: You can trigger the forecast run on demand via a Remote Function Call (RFC). The forecast results are returned via RFC as requested.

Demand Decomposition

You can set UDF to break down the generated forecast by demand influencing factor (DIF) to better explain its underlying causes. This process is called demand decomposition. It allows you to see how much of the total forecast can be attributed to baseline business and how much is due to a specific DIF. Examples of DIFs are offers, prices, tactics, or seasonality. A DIF's influence on the demand can be either positive or negative. UDF writes the demand decomposition results to table /DMF/UFC_TSD.

Forecast Granularity

UDF forecasts demand on the finest granularity (daily). For brick-and-mortar scenarios, this is a single product in a single location. For multichannel scenarios, UDF can additionally forecast by order channel, distribution channel, and sales organization.


The statistical algorithm behind UDF is a Bayesian regression model that allows configuring both additive and multiplicative DIF effects. UDF can handle missing information through general best guesses (“priors”). When modeling the demand and estimating the best values for the parameters of the demand model, UDF balances priors and historical data:

  • Little historical data → Parameter estimates closer to priors

  • Lots of historical data → Parameter estimates closer to data

Hierarchical Priors

Hierarchical priors allow you to enhance the demand modeling of products with little or no historical sales data or promotional data. Examples are new products or products with DIFs not observed before (such as offers, day-of-week effects, seasonality). Those products can “inherit” existing values (parameter estimates) from other products along the product and location hierarchies. You can use the Calculate Hierarchical Priors service in the Schedule Model and Forecasts function for this purpose. Note that you must have completed the initial modeling of your business (that is, modeling results are available).

The generated hierarchical priors are used as input values for demand modeling, where they enhance the understanding of demand at a more granular level than the default values set as global defaults. This improves the basis for demand forecasting.

You can generate hierarchical priors by product hierarchy (such as the article hierarchy or merchandise category hierarchy) and by location hierarchy (such as the master location hierarchy). In the product hierarchy, a product location inherits values from other product locations in the same location. In the location hierarchy, a product location inherits values from the same product location in other locations. This allows you to better understand the DIF effects either across all products of a hierarchy node for a particular location, or across all locations of a hierarchy node for a particular product.

Note Note

For configuration examples, see the long texts of data elements /DMF/HPR_MAX_PROD_LEVELS and /DMF/HPR_MAX_LOC_LEVELS.

End of the note.
Reference Products

You can assign reference products to improve the demand modeling and forecasting of products for which there is little or no historical demand data available (such as new products). To model and forecast on such a new product at a particular location, UDF then uses the historical information and prior values from the assigned reference product at the reference location.

You can set up reference product locations either in your SAP ERP system and receive the master data from there. Or you can set them up directly in DDF. For more information, see Maintain Product Locations.

Placeholder Products

You can create placeholders for products that are still being planned and for which you do not yet have all the information to create them in your SAP ERP system. For example, this is useful during promotion planning or assortment planning.

You create the placeholder product as a temporary product in DDF and assign a reference product to it. You can then model and forecast the demand for the placeholder product with UDF. UDF treats placeholder products the same way as products that you import from or integrate with your SAP ERP system.

To forecast on a specific placeholder product, UDF uses the historical information from the assigned reference product.

Note Note

  • If the reference product was previously modeled, the forecast is scaled by the reference factor. You can define this factor in the placeholder master data. For more information, see Placeholder Product.

  • If the reference product has not been previously modeled or is invalid, the forecast is generated using the prior values.

End of the note.

For more information on how to create and maintain placeholder products in DDF, see Maintain Placeholder Products.

Forecast Confidence Index (FCI)

Note Note

You can use this feature when you create offers in SAP Promotion Management for Retail, one of the consuming applications of UDF. For more information, see SAP Library for SAP Promotion Management for Retail on SAP Help Portal at   Application Help   SAP Library   Promotion Planning   Maintain Offers  .

End of the note.

You can evaluate forecasts based on a forecast confidence index (FCI). The FCI is an indicator of statistical confidence in a particular unit forecast. The FCI is always calculated for a specific product at a specific location, and it is based on the amount of historical information provided to forecast the demand for this product.


  • FCI ranges for quickly evaluating forecasts: You can configure what constitutes a high, medium, or low FCI for your business. Based on your settings, the system not only generates the FCI value for a particular forecast but also qualifies this value as high, medium, or low. For more information about configuring the FCI, see Customizing under   Cross-Application Components   Demand Data Foundation   Modeling and Forecasting   Define Categories for Forecast Confidence Index  .

  • FCI reasons for analyzing low FCIs: The system can also estimate which of the DIFs considered for a particular forecast is most determinant in causing a low FCI value. For example, there might be no sales history available for a specific offer combination. This allows you to take corrective measures, for example, by changing the terms of a planned offer. For an overview of the available FCI reasons, see the Low FCI messages in message class /DMF/FC_INFO (transaction SE91).

More Information

  • Setting up UDF: Administrator's Guide, Demand Data Foundation (DDF) with Unified Demand Forecast (UDF) on SAP HANA and Common Installation Guide for SAP Customer Activity Repository, SAP Assortment Planning for Retail, SAP Promotion Management for Retail. You can find both guides on SAP Service Marketplace at   Installation & Upgrade Guides   Industry Solutions   Industry Solution Guides   SAP for Retail   SAP Customer Activity Repository   SAP Customer Activity Repository 2.0  .

  • Using UDF: Schedule Model and Forecast

  • Visualizing and validating forecasts: Validate Forecasts with UDF Launchpad